Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 3044 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.7121. Min Range: -3.7121

Max Act: 3.7121. Min Act: -0.1700

Data Index: 8764172 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 3.7121. Min Range: -3.7121

Max Act: 3.6417. Min Act: -0.1700

Data Index: 2714037 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.7121. Min Range: -3.7121

Max Act: 3.5965. Min Act: -0.1700

Data Index: 5729184 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.7121. Min Range: -3.7121

Max Act: 3.5807. Min Act: -0.1700

Data Index: 1341308 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 3.7121. Min Range: -3.7121

Max Act: 3.5601. Min Act: -0.1700

Data Index: 2790030 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.7121. Min Range: -3.7121

Max Act: 3.5598. Min Act: -0.1700

Data Index: 2735592 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.7121. Min Range: -3.7121

Max Act: 3.5512. Min Act: -0.1700

Data Index: 653034 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 3.7121. Min Range: -3.7121

Max Act: 3.5590. Min Act: -0.1700

Data Index: 7837627 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.7121. Min Range: -3.7121

Max Act: 3.5660. Min Act: -0.1700

Data Index: 7166418 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.7121. Min Range: -3.7121

Max Act: 3.5748. Min Act: -0.1700

Data Index: 6512955 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 3.7121. Min Range: -3.7121

Max Act: 3.5232. Min Act: -0.1700

Data Index: 2298201 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 3.7121. Min Range: -3.7121

Max Act: 3.5389. Min Act: -0.1700

Data Index: 4519435 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.7121. Min Range: -3.7121

Max Act: 3.5361. Min Act: -0.1700

Data Index: 1045027 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.7121. Min Range: -3.7121

Max Act: 3.5213. Min Act: -0.1700

Data Index: 3324230 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.7121. Min Range: -3.7121

Max Act: 3.5304. Min Act: -0.1700

Data Index: 3909598 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.7121. Min Range: -3.7121

Max Act: 3.5309. Min Act: -0.1700

Data Index: 4831405 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.7121. Min Range: -3.7121

Max Act: 3.5268. Min Act: -0.1700

Data Index: 496027 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 3.7121. Min Range: -3.7121

Max Act: 3.5267. Min Act: -0.1700

Data Index: 4152192 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 3.7121. Min Range: -3.7121

Max Act: 3.5376. Min Act: -0.1700

Data Index: 4941713 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.7121. Min Range: -3.7121

Max Act: 3.5232. Min Act: -0.1700

Data Index: 4976020 (Open Web Text)

Max Activating Token Index: 2